Multi-objective Multiagent Credit Assignment Through Difference Rewards in Reinforcement Learning


Multiagent systems have had a powerful impact on the real world. Many of the systems it studies (air traffic, satellite coordination, rover exploration) are inherently multi-objective, but they are often treated as single-objective prob- lems within the research. A very important concept within multiagent systems is that of credit assignment: clearly quantifying an individual agent’s impact on the overall system performance. In this work we extend the concept of credit assign- ment into multi-objective problems, broadening the traditional multiagent learn- ing framework to account for multiple objectives. We show in two domains that by leveraging established credit assignment principles in a multi-objective setting, we can improve performance by (i) increasing learning speed by up to 10x (ii) reducing sensitivity to unmodeled disturbances by up to 98.4% and (iii) produc- ing solutions that dominate all solutions discovered by a traditional team-based credit assignment schema. Our results s uggest that in a multiagent multi-objective problem, proper credit assignment is as important to performance as the choice of multi-objective algorithm.